an:02100880
Zbl 1046.62065
Kub????ek, Lubom??r; Tesa????kov??, Eva
Confidence regions in nonlinear models with constraints
EN
Acta Univ. Palacki. Olomuc., Fac. Rerum Nat., Math. 42, 43-58 (2003).
00100973
2003
j
62J02 62F30 62F25 62H12
measures of nonlinearity
Summary: There are some difficulties in construction of confidence regions in nonlinear models with constraints. Even if an exact algorithm (in the case of normality) can be derived, the numerical calculation is rather tedious. Thus if a simple algorithm can be find it will be preferred in practice. The aim of the paper is to find a simple criterion which enables us to decide whether it is possible to use algorithms useful in linear models.